Inference provider

Nebius

Headquarters: NL

10

models

10

endpoints

Nebius website preview
Nebius website

Catalogue

Available models

ModelEndpointContextInput /MOutput /MCached input /MCache write /MUptime 1d
GLM 5.1nebius/fp8203K$1.40$4.40——100.00%
GLM 5.2nebius/fp41.0M$1.40$4.40——95.50%
Gemma 3 27Bnebius/fp8110K$0.10$0.30——96.07%
Hermes 4 405Bnebius/fp8131K$1.00$3.00——100.00%
Kimi K2.7 Codenebius/fp4262K$0.95$4.00——100.00%
Nemotron 3 Nano 30B A3Bnebius/fp8262K$0.06$0.24——97.09%
Qwen3 235B A22B Instruct 2507nebius/fp8262K$0.20$0.60——86.16%
Qwen3 30B A3B Instruct 2507nebius/fp8262K$0.10$0.30——90.07%
Qwen3 Embedding 8Bnebius32K$0.01$0.00——100.00%
gpt-oss-120bnebius/fp4131K$0.15$0.60——100.00%